infery
← All models

Flux Kontext Dev

flux-kontext-dev

Image editby Black Forest Labs

FLUX.1 Kontext dev is an image-to-image model that edits your images with text. This is an open weights, open code, open source model. Created by Black Forest Labs. Try all FLUX.1 Kontext models now!

images

Details

Accepts
image

Pricing

Price
3.13 cr / image

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedintegerRandom seed for reproducible generation. Leave blank for random.
promptrequiredstringText description of what you want to generate, or the instruction on how to edit the given image.
guidancenumberGuidance scale for generation
input_imagestringImage to use as reference. Must be jpeg, png, gif, or webp.
aspect_ratioenum: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.
output_formatenum: webp, jpg, pngOutput image format
output_qualityintegerQuality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
num_inference_stepsintegerNumber of inference steps
disable_safety_checkerbooleanDisable NSFW safety checker
image_urlstringThe URL of the image to edit. Max width: 14142px, Max height: 14142px, Timeout: 20s
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.
num_imagesintegerThe number of images to generate.
accelerationstringenum: none, regular, highThe speed of the generation. The higher the speed, the faster the generation.
guidance_scalenumber The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
resolution_modestringenum: auto, match_input, 1:1, 16:9, 21:9, 3:2 Determines how the output resolution is set for image editing. - `auto`: The model selects an optimal resolution from a predefined set that best matches the input image's aspect ratio. This is the recommended setting for most use cases as it's what the model was trained on. …
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.